Gaussianization for Multivariate, High-dimensional Earth Observation data Analysis

2021 ◽  
Author(s):  
J. Emmanuel Johnson ◽  
Maria Piles ◽  
Valero Laparra ◽  
Gustau Camps-Valls
Keyword(s):  
Information Theory ◽  
Data Analysis ◽  
Hyperspectral Image ◽  
Generative Models ◽  
Earth Observation ◽  
Observation Data ◽  
Earth System ◽  
Multivariate Gaussian Distribution ◽  
System Data ◽  
Earth Observation Data

<p>Long-standing questions in multivariate statistics, information theory and machine learning reduce to estimating multivariate densities. However, this is still an unresolved problem and one of the biggest challenge in general, and for Earth system data analysis in particular, due to the high dimensionality (spatial, temporal and/or spectral) of the data streams. Gaussianization is a class of generative models (normalizing flows) that is effective in computing density estimates by using  a sequence of composite invertible transformations which transform data from its original domain to a multivariate Gaussian distribution. The methodology in turn allows us to estimate information theory measures (ITMs), which are relevant for the analysis and characterization of Earth system data superseding the mean, variance and correlation, as higher order measures, thereby capturing more complexity and providing more insight into various problems. We show that our Rotation-Based Iterative Gaussianization (RBIG) method allows us to compute ITMs from multivariate (spatio-spectral-temporal) Earth data efficiently in both computation and memory terms, directly from the Gaussianizing transformation, while being robust to data dimensionality . We demonstrate how Gaussianization is useful in various Earth observation data analysis problems, from hyperspectral image analysis to drought detection in data cubes.</p>

scholarly journals Editorial of Special Issue “Machine and Deep Learning for Earth Observation Data Analysis”

2021 ◽  
Vol 13 (14) ◽  
pp. 2758
Author(s):  
Vasileios Syrris ◽  
Sveinung Loekken
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Data Analysis ◽  
Earth Observation ◽  
Observation Data ◽  
Earth System ◽  
Special Issue ◽  
The Earth ◽  
Comprehensive Information ◽  
Earth Observation Data

Earth observation and remote sensing technologies provide ample and comprehensive information regarding the dynamics and complexity of the Earth system [...]

scholarly journals A Survey on Gaussian Processes for Earth-Observation Data Analysis: A Comprehensive Investigation

2016 ◽  
Vol 4 (2) ◽  
pp. 58-78 ◽  
Author(s):  
Gustau Camps-Valls ◽  
Jochem Verrelst ◽  
Jordi Munoz-Mari ◽  
Valero Laparra ◽  
Fernando Mateo-Jimenez ◽  
...  
Keyword(s):  
Data Analysis ◽  
Gaussian Processes ◽  
Earth Observation ◽  
Observation Data ◽  
Comprehensive Investigation ◽  
Earth Observation Data

Jaxa's Earth Observation Data Analysis on Covid-19

2021 ◽  
Author(s):  
Ko Hamamoto ◽  
Akihiko Kuze ◽  
Takeo Tadono ◽  
Shinichi Sobue ◽  
Junichiro Ishizawa ◽  
...  
Keyword(s):  
Data Analysis ◽  
Earth Observation ◽  
Observation Data ◽  
Earth Observation Data

scholarly journals Satellite Image Time Series Analysis for Big Earth Observation Data

2021 ◽  
Vol 13 (13) ◽  
pp. 2428
Author(s):  
Rolf Simoes ◽  
Gilberto Camara ◽  
Gilberto Queiroz ◽  
Felipe Souza ◽  
Pedro R. Andrade ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Data Analysis ◽  
Time Series Analysis ◽  
Satellite Image ◽  
Earth Observation ◽  
Observation Data ◽  
Accuracy Measurement ◽  
Series Analysis ◽  
Earth Observation Data

The development of analytical software for big Earth observation data faces several challenges. Designers need to balance between conflicting factors. Solutions that are efficient for specific hardware architectures can not be used in other environments. Packages that work on generic hardware and open standards will not have the same performance as dedicated solutions. Software that assumes that its users are computer programmers are flexible but may be difficult to learn for a wide audience. This paper describes sits, an open-source R package for satellite image time series analysis using machine learning. To allow experts to use satellite imagery to the fullest extent, sits adopts a time-first, space-later approach. It supports the complete cycle of data analysis for land classification. Its API provides a simple but powerful set of functions. The software works in different cloud computing environments. Satellite image time series are input to machine learning classifiers, and the results are post-processed using spatial smoothing. Since machine learning methods need accurate training data, sits includes methods for quality assessment of training samples. The software also provides methods for validation and accuracy measurement. The package thus comprises a production environment for big EO data analysis. We show that this approach produces high accuracy for land use and land cover maps through a case study in the Cerrado biome, one of the world’s fast moving agricultural frontiers for the year 2018.

Our goal is to establish the earth observation data in the business world Unser Ziel ist es, die Erdbeobachtungsdaten in der Geschäftswelt zu etablieren

GIS Business ◽  
2019 ◽  
Vol 12 (3) ◽  
pp. 12-14
Author(s):  
Eicher, A
Keyword(s):  
Earth Observation ◽  
Observation Data ◽  
Business World ◽  
The Earth ◽  
Earth Observation Data

Our goal is to establish the earth observation data in the business world Unser Ziel ist es, die Erdbeobachtungsdaten in der Geschäftswelt zu etablieren

Mapping slums and model population density using earth observation data and open source solutions

2019 ◽  
Author(s):  
Tais Grippa ◽  
Stefanos Georganos ◽  
Sabine Vanhuysse ◽  
Moritz Lennert ◽  
Nicholus Mboga ◽  
...  
Keyword(s):  
Population Density ◽  
Open Source ◽  
Earth Observation ◽  
Observation Data ◽  
Model Population ◽  
Earth Observation Data

scholarly journals Examining the Economic and Environmental Impacts of COVID-19 Using Earth Observation Data

2020 ◽  
Vol 13 (1) ◽  
pp. 5
Author(s):  
William Straka ◽  
Shobha Kondragunta ◽  
Zigang Wei ◽  
Hai Zhang ◽  
Steven D. Miller ◽  
...  
Keyword(s):  
Air Quality ◽  
Los Angeles ◽  
Environmental Impacts ◽  
Demographic Data ◽  
The United States ◽  
Earth Observation ◽  
Observation Data ◽  
Washington Dc ◽  
Mobility Data ◽  
Earth Observation Data

The COVID-19 pandemic has infected almost 73 million people and is responsible for over 1.63 million fatalities worldwide since early December 2019, when it was first reported in Wuhan, China. In the early stages of the pandemic, social distancing measures, such as lockdown restrictions, were applied in a non-uniform way across the world to reduce the spread of the virus. While such restrictions contributed to flattening the curve in places like Italy, Germany, and South Korea, it plunged the economy in the United States to a level of recession not seen since WWII, while also improving air quality due to the reduced mobility. Using daily Earth observation data (Day/Night Band (DNB) from the National Oceanic and Atmospheric Administration Suomi-NPP and NO2 measurements from the TROPOspheric Monitoring Instrument TROPOMI) along with monthly averaged cell phone derived mobility data, we examined the economic and environmental impacts of lockdowns in Los Angeles, California; Chicago, Illinois; Washington DC from February to April 2020—encompassing the most profound shutdown measures taken in the U.S. The preliminary analysis revealed that the reduction in mobility involved two major observable impacts: (i) improved air quality (a reduction in NO2 and PM2.5 concentration), but (ii) reduced economic activity (a decrease in energy consumption as measured by the radiance from the DNB data) that impacted on gross domestic product, poverty levels, and the unemployment rate. With the continuing rise of COVID-19 cases and declining economic conditions, such knowledge can be combined with unemployment and demographic data to develop policies and strategies for the safe reopening of the economy while preserving our environment and protecting vulnerable populations susceptible to COVID-19 infection.

Sign in / Sign up

Export Citation Format

Share Document